Technique for Classifying Odor Substances and Their Intensity with a PZT Thin-Film Piezoelectric Mobile Sensor
PZT圧電薄膜型モバイルニオイセンサによる臭気成分の嗅ぎ分け技術
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.):¥1,100 Members (tax incl.):¥880
- Publication code
- 20216233
- Paper/Info type
- Proceedings (Autumn)
No.132-21
- Pages
- 1-4(Total 4 p)
- Date of publication
- Oct 2021
- Publisher
- JSAE
- Language
- Japanese
- Event
- 2021 JSAE Annual Congress (Autumn) [Online]
Detailed Information
Author(J) | 1) 塩貝 有里, 2) 坂東 靜, 3) 井野 龍之介, 4) 久保田 悠美, 5) 大西 孝一 |
---|---|
Author(E) | 1) Yuri Shiogai, 2) Shizuka Bando, 3) Ryunosuke Ino, 4) Yumi Kubota, 5) Koichi Onishi |
Affiliation(J) | 1) 日産自動車, 2) 日産自動車, 3) 日産自動車, 4) 日産自動車, 5) 日産自動車 |
Affiliation(E) | 1) Nissan Motor, 2) Nissan Motor, 3) Nissan Motor, 4) Nissan Motor, 5) Nissan Motor |
Abstract(J) | 特定悪臭物質のうち分子構造により分類された代表的な臭気成分について,認知閾値濃度以上の3段階強度で車室内臭気を小型ニオイセンサで計測した.180の感応膜素子の特徴量を機械学習にかけて成分および強度判別を実施したところ,15-30℃,30-50%の温湿度条件で99%以上の精度で判別可能であった. Translation |
Abstract(E) | The authors measured typical odor substances, which were classified according to molecular structure, with a portable smell sensor at three concentration levels higher than a cognitive threshold in vehicle, and conducted discriminant analysis of the odor substances by machine learning with the feature values of 180 membrane films. The result showed that the accuracy was more than 99 percent under the temperature condition from 15 to 30 degrees Celsius and the humidity condition from 30 to 50 percent. |